Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hamzaPixl/pixl-ai --skill investigategit clone --depth 1 https://github.com/hamzaPixl/pixl-aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hamzapixl/pixl-ai/investigate)<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/investigate"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/investigate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/investigate"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/investigate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.01424 |
| Opus 5.5 | $0.00021 | $0.00570 |
| Sonnet 5.5 | $0.00010 | $0.00285 |
| Haiku 4.5 | $0.00005 | $0.00142 |
Grade A, and why
investigate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Structured debugging that enforces investigation before fixing. Inspired by the "3-strike rule" — you must understand the root cause before writing any fix. Every fix requires a regression test.
How this differs from other skills:
/runbook— live incident response for production systems. This skill is for code-level debugging./self-review-fix-loop— iterative review-and-fix loop for open changes. This skill starts from a symptom and traces to root cause./test-runner— runs tests. This skill debugs WHY tests (or features) fail.
Phase 1: Reproduce (Read-Only)
Goal: Confirm the bug exists and define the exact failure condition.
- Capture the symptom: What exactly is failing? Error message, unexpected behavior, test failure?
- Reproduce reliably: Find the minimal steps to trigger the bug
- Run the failing test:
pytest <file>::<test> -v --tb=longorvitest run <file> -t "<test>" - Or reproduce manually via the described steps
- Run the failing test:
- Define the contract: What SHOULD happen vs what DOES happen?
- Scope the blast radius: Is this isolated or does it affect other areas?
Output:
SYMPTOM: <exact error or unexpected behavior>
REPRODUCTION: <minimal steps to trigger>
EXPECTED: <what should happen>
ACTUAL: <what does happen>
SCOPE: <isolated | cross-cutting | unknown>
Do NOT write any fixes yet. Phase 1 is strictly read-only.
Phase 2: Diagnose (Read-Only)
Goal: Narrow to a single root cause. Follow the evidence, not assumptions.
Diagnostic Ladder
Work through in order — stop when you find the root cause:
- Read the error: Parse the full stack trace. What line, what function, what input?
- Trace the data flow: Follow the input from entry point to failure point
- Use Grep to find callers:
grep -r "functionName" --include="*.ts" - Read each file in the call chain
- Use Grep to find callers:
- Check recent changes:
git log --oneline -20 -- <affected-files>andgit diff HEAD~5 -- <affected-files> - Compare working vs broken: If it worked before, what changed?
git bisectif needed - Check dependencies: Version changes, config changes, environment differences
- Inspect state: Add temporary logging or use debugger to inspect runtime values
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 139 lines · 52 tokens per session scan A 2a239f4ee905
investigate is a skill published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 6mo ago), licensed MIT. It adds 52 tokens to every session and 1,424 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
validate-fix
Prove a fix works before declaring done — re-run the failing test, run the full suite, typecheck, lint, and harden against recurrence. Use after implementing a bug fix, when user says "is this fixed?", or before closing an investigation.
triage-issue
Bug triage: explores codebase for root cause, files GitHub issue with TDD fix plan. Triggers: triage, investigate bug, fix plan, root cause, file issue, bug report.